T SQL Cte delete where group by is greater than 1 - sql

Question

I'm using SQL Server 2016. I have the below table:
SKU Mkt Week Cost Code
ABC 05 1 10 100
ABC 05 2 12 100
DEF 05 3 20 100
DEF 05 3 25 125
XYZ 08 1 10 100
XYZ 08 2 12 100
XZY 08 2 14 125
This is the desired result:
SKU Mkt Week Cost Code
ABC 05 1 10 100
ABC 05 2 12 100
DEF 05 3 25 125
XYZ 08 1 10 100
XZY 08 2 14 125
So if a SKU\Mkt\Week\Cost exist more than once, I want to keep the record where code = 125 and delete the row where the code is 100.
I'm using the below Cte:
;WITH CTE AS
(
SELECT *,
RN = ROW_NUMBER() OVER( PARTITION BY SKU, Mkt, Week
ORDER BY SKU, Mkt, Week)
FROM [table]
WHERE code = 100
)
DELETE FROM CTE
WHERE RN > 1
However, the Cte doesnot delete anything -what am I missing?

Answer 1

Based on the query and sample data you have provided, You need to note to this section of the cte inner query:
WHERE code = 100
when this filter applied you have the following data:
SKU Mkt Week Cost Code
ABC 05 1 10 100
ABC 05 2 12 100
DEF 05 3 20 100
which will get the 1 as Row_Number()'s output!, so running the following query will not effect any rows:
DELETE FROM CTE
WHERE RN > 1
To achieve the desired result you need to remove the WHERE section in CTE's inner query.
;WITH CTE AS
(
SELECT *,
RN = ROW_NUMBER() OVER( PARTITION BY SKU, Mkt, Week
ORDER BY SKU, Mkt, Week, Cost DESC) --Code/Cost DESC <==== Note this too
FROM [table]
--WHERE code = 100 <========== HERE, I've commented it
)
DELETE FROM CTE
WHERE RN > 1
You need to also add the Cost DESC or Code Desc to Row_Number()'s Order By section.

Answer 2

Ranking function will be evaluated in the select statement , which means the where clause WHERE code = 100 is evaluated before ROW_NUMBER() and so it has already removed the rows with code 125. Use order by Code as well and then apply the code=100 check when deleting from the CTE
;WITH CTE AS
(
SELECT *,
RN = ROW_NUMBER() OVER( PARTITION BY SKU, Mkt, Week
ORDER BY SKU, Mkt, Week,Code DESC)
FROM tt1
)
DELETE FROM CTE
WHERE RN > 1
AND CODE = 100

Answer 3

Try below query to get the desired result -
Sample data and Query
Declare #Table table
(SKU varchar(20), Mkt int, [Week] int, Cost int, Code int)
Insert into #Table
values
( 'ABC', 05 , 1, 10 , 100),
( 'ABC' , 05 , 2 , 12 , 100),
('DEF' ,05 , 3 , 20 , 100),
('DEF' ,05 , 3 ,25 , 125),
('XYZ' , 08 , 1 ,10 , 100),
('XYZ' , 08 , 2 ,12 , 100),
('XYZ' , 08, 2 ,14, 125)
;WITH CTE AS
(
SELECT *,
RN = ROW_NUMBER() OVER( PARTITION BY SKU, Mkt, Week
ORDER BY SKU, Mkt, Week, code desc)
FROM #Table
)
delete from Cte where RN > 1

Answer 4

Along with moving your Where statement, I believe you also want a second cte to work with the records you are identifying... In the following your first cte identifies the duplicate records while the second cte isolates them so you can perform your delete against those SKUs
Table
Create Table #tbl
(
SKU VarChar(10),
Mkt VarChar(10),
Week Int,
Cost Int,
Code Int
)
Insert Into #tbl Values
('ABC','05',1,10,100),
('ABC','05',2,12,100),
('DEF','05',3,20,100),
('DEF','05',3,25,125),
('XYZ','08',1,10,100),
('XYZ','08',2,12,100),
('XYZ','08',2,14,125)
Query
;WITH CTE AS
(
SELECT *,
RN = ROW_NUMBER() OVER( PARTITION BY SKU, Mkt, Week
ORDER BY SKU, Mkt, Week)
FROM #tbl
--WHERE code = 100
)
, cte1 As
(
Select sku from cte where rn > 1
)
DELETE c FROM CTE c inner join cte1 c1 On c.SKU = c1.SKU
WHERE c.Code = 100
Select * From #tbl
Result (Your 'desired result' example removed an XYZ record where the week was not duplicated?)
SKU Mkt Week Cost Code
ABC 05 1 10 100
ABC 05 2 12 100
DEF 05 3 25 125
XYZ 08 1 10 100
XYZ 08 2 12 100
XZY 08 2 14 125

Answer 5

Your CTE statement is only considering rows with code = 100. If you remove it, then CTE will rank based on all rows from the table. Using this, first find out which combination of have multiple rows. Then, among these combinations, identify rows with code = 100 and delete them.
create table #e1
(
SKU varchar(50)
,Mkt varchar(50)
,_Week int
,Cost int
,_code int
)
insert into #e1(SKU, Mkt, _Week, Cost, _code)
select 'ABC', '05', 1, 10, 100 UNION
SELECT 'ABC', '05', 2, 12, 100 union
SELECT 'DEF', '05', 3, 20, 100 UNION
SELECT 'DEF', '05', 3, 25, 125 UNION
SELECT 'XYZ', '08', 1, 10, 100 UNION
SELECT 'XYZ', '08', 2, 12, 100 UNION
SELECT 'XZY', '08', 2, 14, 125
delete s
from
#e1 s
JOIN
(
SELECT SKU, Mkt, _Week
FROM #e1
group by
SKU, Mkt, _Week
having count(1) > 1
) m
ON
s.SKU = m.sku and s.mkt = m.mkt and s._Week = m._Week
WHERE s._code = 100

Answer 6

Create table #tab1 (SKU varchar(50),Mkt varchar(50),[Week] varchar(50),Cost varchar(50),Code varchar(50))
insert into #tab1
select 'ABC','05','1','10','100'
union
select 'ABC','05','2','12','100'
union
select 'DEF','05','3','20','100'
union
select 'DEF','05','3','25','125'
union
select 'XYZ','08','1','10','100'
union
select 'XYZ','08','2','12','100'
union
select 'XYZ','08','2','14','125'
delete t from #tab1 t
inner join (select t1.SKU,t1.Mkt,t1.[Week],t1.Cost as Cost,t1.Code as Code,ROW_NUMBER()over(partition by t1.SKU,t1.Mkt,t1.[Week] order by t1.Cost desc,t1.Code desc ) as rno
from #tab1 t1
) c on c.SKU = t.SKU and c.Mkt = t.Mkt and c.Cost = t.Cost and c.[Week] = t.[Week] and c.Code = t.Code
where c.rno = 2
select * from #tab1
Output:
SKU Mkt Week Cost Code
ABC 05 1 10 100
ABC 05 2 12 100
DEF 05 3 25 125
XYZ 08 1 10 100
XYZ 08 2 14 125